@di_bogdanov Profile picture

Dmitry Bogdanov

@di_bogdanov

Music/audio technology & MIR. Senior researcher @mtg_upf, software engineer @Essentia_MTG. Music @Permutation_BCN.

Similar User
Stefan Lattner photo

@deeplearnmusic

Javier Nistal photo

@latentspaces

MTG-UPF photo

@mtg_upf

Eduardo Fonseca photo

@edfonseca_

Justin Salamon photo

@justin_salamon

Carl Thomé photo

@carlthome

Jordi Pons photo

@jordiponsdotme

ISMIR Conference photo

@ISMIRConf

Pablo Alonso Jiménez photo

@pablo__alonso

Magdalena Fuentes photo

@mfu3ntes

Yi-Hsuan Yang photo

@affige_yang

Pedro Sarmento @ ISMIR 2024 photo

@umpedronosapato

Emmanouil Benetos photo

@emmanouilb

Marius Miron photo

@nkundiushuti

Elio Quinton photo

@elio_elioo

New dataset of musical versions, built from public metadata on @discogs We identified 1.9M versions across 348K music works, over 25% of which we mapped to official music uploads on YouTube. 💾 Dataset: mtg.github.io/discogs-vi-dat… 📄 Paper at #ISMIR2024: arxiv.org/abs/2410.17400

Tweet Image 1

I'll be in San Francisco next week for #ISMIR2024 to present our new musical version identification (VI) dataset, Discogs-VI — the largest dataset of its kind to date! Discogs-VI provides extensive metadata, links to official YouTube uploads, and pre-computed CQT features.



The Song Describer Dataset is gaining some traction and is being used in the MIREX 2024 Music Description & Captioning task this year at #ISMIR2024.

📢MIREX 2024 Task 6: Music Captioning Task is open for submission! 🔔We will invite outstanding teams to submit their technical report to the MIREX track at @ISMIRConf . DDL: October 15th, 2024 (AOE time) Homepage: music-ir.org/mirex/wiki/202… Submission: codabench.org/competitions/3…

Tweet Image 1


New paper from our team for the #icassp2024 Workshop on Explainable AI for Speech and Audio.

Excited to present our paper on interpretable music classification at #icassp2024's XAI-SA workshop in Seoul this Monday, April 15th (2nd oral session, 14:00 KST)! 📝pre-print: arxiv.org/abs/2402.09318 🔈examples: palonso.github.io/pecmae 💻code: github.com/palonso/pecmae [1/6]🧵👇



I am happy to announce that we'll be presenting our music analysis software and AI models @Essentia_MTG and related activities of @mtg_upf at the Sónar 2024 Project Area, June 13 to 15. @sonarfestival @sonarplusd 🔊⚡ w/ @pablo__alonso, @jorgemarcosf

Tweet Image 1

We've opened new PhD positions at MTG! Covering topics of sound and music representation learning, multi-modal music processing, machine listening, generative music, computational musicology, and music performance analysis. 👇🎓

6 PhD positions open in the context of the UPF-BMAT Chair on AI and Music, starting in October 2024. Applications until March 19th: upf.edu/web/mtg/home/-…

Tweet Image 1


We released the Song Describer Dataset of ~1.1K crowd-sourced music captions for 706 open-access audio tracks from MTG-Jamendo—work led by @Ilaria__Manco and Benno Weck, with @philtgun, @MinzWon, and colleagues. Check our paper for the ML for Audio workshop at #NeurIPS2023. 👇

We've released the Song Describer Dataset, an evaluation set of ~1.1k human-written music captions collected through our open-source annotation platform, to be presented at the ML for Audio Workshop at #NeurIPS2023! Paper: arxiv.org/abs/2311.10057 Code: github.com/mulab-mir/song…



Replicate demo for tempo BPM estimation algorithms available in Essentia (degara, multifeature, percival, tempocnn): replicate.com/mtg/essentia-b…

Tweet Image 1

We've updated Essentia with a new music representation model based on transformers and trained on music style metadata in @discogs Useful for genre classification (400 styles) and downstream auto-tagging tasks. This work, led by @pablo__alonso, will be presented at #ISMIR2023 👇

Tweet Image 1

✍️New model out✍️ MAEST is an open music representation model trained in music style classification. 🎙️Conf: Accepted in #ISMIR2023 📄Paper: hdl.handle.net/10230/58023 💻Code: github.com/palonso/MAEST ⚙️Essentia: essentia.upf.edu/models.html#ma… 🤗 HF: huggingface.co/mtg-upf 🧵👇 [1/6]



New paper at #ICASSP2023 led by @pablo__alonso for his internship @likeutopiamusic It investigates using information about track sequences and co-occurrences in playlists for representation learning, building upon our previous work @mtg_upf that used simple editorial metadata.👇

At this #ICASSP2023, we’ll be presenting our work: “Pre-Training Strategies Using Contrastive Learning and Playlist Information for Music Classification and Similarity.” We show that playlist information is beneficial for learning music representations.👇 doi.org/10.48550/arXiv…



Dmitry Bogdanov Reposted

The MTG participates in #ICASSP2023 with six papers in which MTG researchers are involved: Benno Weck, Nazif Can Tamer, @pablo__alonso, @di_bogdanov, Pablo Zinemanas, @rajsuryan, @plachouras, @nkundiushuti, Lonce Wyse, @fxavierserra upf.edu/web/mtg/home/-…

Open Preview for #ICASSP2023 is now available on @IEEEXplore! Available through June 10, you can now browse all the papers that were accepted to ICASSP 2023, free of charge. Browse research here: hubs.la/Q01N_PdX0



Check out this article by @kpeiro for a summary of our recent project at @mtg_upf surveying the opinions of over 100 music and tech professionals on the impact of AI and other emerging technologies. 👇 upf.edu/web/mtg/ai-and…

We have published the article "How will AI coexist with human music? The future is now" by @kpeiro, on the impact of AI in the music sector. A result of the project "Challenges and Opportunities in Music Tech" w/ @music_aire @bcn_ajuntament Read it here: upf.edu/web/mtg/ai-and…

Tweet Image 1


Dmitry Bogdanov Reposted

We're getting closer to having a CC-licensed music-text dataset collected through Song Describer, but we're still looking for contributions: song-describer.streamlit.app. From today, there will be new prizes for top contributors each week, so one more reason to get annotating ✏️🎹

Interested in language and music? 🎧 💬 We’ve just launched Song Describer, an open-source annotation platform featuring CC-licensed music that anyone can annotate with natural language descriptions: song-describer.streamlit.app



Dmitry Bogdanov Reposted

We are looking for a senior researcher to join the MTG. Applications open until February 13th. Information here: upf.edu/web/mtg/home/-…


Dmitry Bogdanov Reposted

“AI models for Sound and Music Applications” (AISMA), new Proof of Concept project at the MTG funded by @CienciaGob @AgEInves #NextGenerationEU #PlanDeRecuperación: upf.edu/web/mtg/home/-…

Tweet Image 1

We added an option to download a lower-bitrate mono audio version of the MTG-Jamendo dataset (156 GB instead of 508 GB for over 55,000 full audio tracks labeled with almost 200 tags by genres, instruments, and moods/themes) and a fast download mirror. 💾🌐 mtg.github.io/mtg-jamendo-da…


Dmitry Bogdanov Reposted

Interested in language and music? 🎧💬Participate in Song Describer, a platform for collecting textual descriptions of music recordings upf.edu/web/mtg/home/-…

Tweet Image 1

At this #ISMIR2022, we presented a new benchmark dataset of relative arousal/valence annotations for validating audio models for music emotion recognition. 📄 Paper: hdl.handle.net/10230/54181 🔊 Dataset: mtg.github.io/musav-dataset/ w/ @xavi_lizarraga, @pablo__alonso, @fxavierserra


We did a paper for this #ISMIR2022, putting to use publicly available editorial metadata from my favorite music database, @discogs, to train audio models targeting music classification (400 styles) + contrastive learning by same track/release/artist/record label associations. 👇

Had an amazing week at Bengaluru attending #ISMIR2022! Amazing conference, great food and people!! Got a chance to present our work “Music representation learning based on editorial metadata from Discogs”. w/ @di_bogdanov and @fxavierserra 🧵⬇️⬇️



Dmitry Bogdanov Reposted

TODAY from 4PM: Challenges and Opportunities in Music Tech - open debate. We will discuss about the impact of music tech in the music sector with @robclouth, Marcelo Estrella, @bzzzbip, @annaxambo, @CalvoGoncal, @fgouyon, @jordiponsdotme, @musikalkemist upf.edu/web/mtg/home/-…

Tweet Image 1

Today at 16:00 CET we are hosting an open debate on the impact of new music technology with two panels on music creation and audiences. @kpeiro and I will ask some questions about the future of music listening to @fgouyon, @CalvoGoncal, @jordiponsdotme, and @musikalkemist 👇

Next week we will organize two panels and open discussion on the challenges and opportunities of music technology for the music sector. Do you want to participate and contribute with your opinions? 🗓️13 Dec 4PM at UPF and online. Info and registrations: upf.edu/web/mtg/home/-…

Tweet Image 1


Loading...

Something went wrong.


Something went wrong.